Added videos to Generative AI LP modules

Author: GraemeMalcolm

learn-pr/wwl-data-ai/foundry-sdk/includes/01-introduction.md

@@ -1,6 +1,19 @@
+::: zone pivot="video"
+
+>[!VIDEO https://learn-video.azurefd.net/vod/player?id=54781308-ebf7-4fb5-91a9-c5c878d91ec3]
+
+::: zone-end
+
+::: zone pivot="text"
+
 Developers creating AI solutions with Microsoft Foundry need to work with a combination of services and software frameworks. When developing a generative AI chat application, you can choose from a range of options to write the code needed to build effective AI apps on Azure.
 
 In this module, you'll learn how to choose the appropriate endpoint, SDK, authentication, and chat API options to build a generative AI chat application.
 
+::: zone-end
+
 > [!NOTE]
+> We recognize that different people like to learn in different ways. You can choose to complete this module in video-based format or you can read the content as text and images. The text contains greater detail than the videos, so in some cases you might want to refer to it as supplemental material to the video presentation.
+
+> [!CAUTION]
 > Some Microsoft Foundry features are currently in preview. Details described in this module are subject to change.

learn-pr/wwl-data-ai/foundry-sdk/includes/02-chat-playground.md

@@ -1,3 +1,13 @@
+::: zone pivot="video"
+
+>[!VIDEO https://learn-video.azurefd.net/vod/player?id=e1c66b97-da7f-454f-a866-d1167918f8b8]
+
+> [!TIP]
+> See the **Text and images** tab for more details!
+
+::: zone-end
+
+::: zone pivot="text"
 Before you write code to build a generative AI chat application, it's helpful to explore what your project can do through the Foundry portal. The portal provides interactive tools for testing models and generating code samples that you can use as starting points for your applications.
 
 [![Screenshot of the Model playground in Microsoft Foundry portal.](../media/foundry-playground.png)](../media/foundry-playground.png#lightbox)
@@ -41,3 +51,5 @@ The typical workflow for building an AI application with Microsoft Foundry looks
 This approach lets you quickly prototype and validate your ideas before investing time in development.
 
 In the next unit, you'll learn about the available endpoints and SDKs you can use to develop a client application.
+
+::: zone-end

learn-pr/wwl-data-ai/foundry-sdk/includes/03-microsoft-foundry-sdk.md

@@ -1,3 +1,13 @@
+::: zone pivot="video"
+
+>[!VIDEO https://learn-video.azurefd.net/vod/player?id=e7c5ceeb-74a6-4230-9368-abf1abc5005b]
+
+> [!TIP]
+> See the **Text and images** tab for more details!
+
+::: zone-end
+
+::: zone pivot="text"
 Microsoft Foundry provides flexibility for developing generative AI chat applications. Before you start development, it's important to understand the options that are available, and how to decide which of them to use. Some considerations for developing an application include:
 
 - **Endpoints**: Microsoft Foundry projects provide two endpoints that you can use to connect to and consume project assets, such as model deployments, from client applications. Each project has both a *Project endpoint* and an *Azure OpenAI endpoint*.
@@ -193,3 +203,5 @@ Use the OpenAI SDK when you need maximum compatibility with the OpenAI API:
 The OpenAI SDK is ideal for model inference workloads where you want existing OpenAI code to work with minimal changes. However, this approach doesn't provide Foundry-specific features like agents or evaluations.
 
 Microsoft Foundry gives you flexibility in how you build AI applications. Use the Foundry SDK with `AIProjectClient` when you need project-level features like agents, evaluations, tracing, and connections. Use the OpenAI SDK when you need straightforward model inference with maximum OpenAI compatibility. Both SDKs work with your Foundry project endpoint, so you can combine them as needed in your applications. You can also use both SDKs together in the same application—the Foundry SDK for project features and the OpenAI SDK for model inference.
+
+::: zone-end

learn-pr/wwl-data-ai/foundry-sdk/includes/04-responses-api.md

@@ -1,3 +1,14 @@
+::: zone pivot="video"
+
+>[!VIDEO https://learn-video.azurefd.net/vod/player?id=8461a925-d01f-4b56-8092-dfe9c406861e]
+
+> [!TIP]
+> See the **Text and images** tab for more details!
+
+::: zone-end
+
+::: zone pivot="text"
+
 The OpenAI *Responses* API brings together capabilities from two previously separate APIs (*ChatCompletions* and *Assistants*) in a unified experience. It provides stateful, multi-turn response generation, making it ideal for conversational AI applications. You can access the Responses API through an OpenAI-compatible client using either the Foundry SDK or the OpenAI SDK.
 
 ## Understanding the Responses API
@@ -334,3 +345,5 @@ asyncio.run(stream_response())
 ```
 
 By using the *Responses* API through the Microsoft Foundry SDK, you can build sophisticated conversational AI applications that maintain context, support multiple model types, and provide a responsive user experience.
+
+::: zone-end

learn-pr/wwl-data-ai/foundry-sdk/includes/05-openai-api.md

@@ -1,3 +1,13 @@
+::: zone pivot="video"
+
+>[!VIDEO https://learn-video.azurefd.net/vod/player?id=c770294d-763e-49ef-bfbf-e67cb255880c]
+
+> [!TIP]
+> See the **Text and images** tab for more details!
+
+::: zone-end
+
+::: zone pivot="text"
 The OpenAI *ChatCompletions* API is commonly used across generative AI models and platforms. Although the *Responses* API is recommended for new project development, it's likely that you'll encounter scenarios where the *ChatCompletions* API is useful for code maintenance or cross-platform compatibility.
 
 ## Submitting a prompt
@@ -125,3 +135,5 @@ Assistant: Goodbye!
 Each new user prompt and completion is added to the conversation, and the entire conversation history is submitted in each turn.
 
 While not as fully featured as the *Responses* API, the *ChatCompletions* API is well established in the generative AI model ecosystem, so it's useful to be familiar with it.
+
+::: zone-end

learn-pr/wwl-data-ai/foundry-sdk/includes/08-summary.md

@@ -1,3 +1,14 @@
+::: zone pivot="video"
+
+>[!VIDEO https://learn-video.azurefd.net/vod/player?id=f62dd8de-d387-427a-a132-8e19016a7c2b]
+
+> [!TIP]
+> See the **Text and images** tab for more details!
+
+::: zone-end
+
+::: zone pivot="text"
+
 Microsoft Foundry provides two SDKs for building AI applications. The Foundry SDK gives you access to project-level features like agents, evaluations, tracing, and connections. The OpenAI SDK provides model inference with full OpenAI API compatibility.
 
 ## Key takeaways
@@ -8,7 +19,11 @@ In this module, you learned how to:
 - **Use the OpenAI SDK** with the Foundry project and Azure OpenAI endpoints for model inferencing
 - **Generate responses** with the *Responses* and *ChatCompletions* APIs and manage conversations
 
-## Next steps
+::: zone-end
+
+## Further reading
+
+For more information about the topics discussed in this module, see the following resources:
 
 - [Microsoft Foundry SDK overview](/azure/ai-foundry/how-to/develop/sdk-overview)
 - [Responses API documentation](/azure/ai-foundry/openai/how-to/responses)

learn-pr/wwl-data-ai/model-catalog-evaluate/includes/1-introduction.md

@@ -1,3 +1,11 @@
+::: zone pivot="video"
+
+>[!VIDEO https://learn-video.azurefd.net/vod/player?id=42158315-f597-41f5-80a7-52633f96f410]
+
+::: zone-end
+
+::: zone pivot="text"
+
 Building effective generative AI applications requires selecting the right foundation model for your specific use case. With thousands of models available, you need a structured approach to discover, compare, deploy, and validate that a model meets your requirements.
 
 Consider a scenario where you're building an AI-powered customer support chatbot for a retail company. You need to select a language model that can understand customer questions, provide accurate responses, and maintain appropriate tone and safety standards. But how do you choose from the vast catalog of available models? How do you know if a model performs well for your specific needs? And once deployed, how do you measure and improve its performance?
@@ -13,3 +21,8 @@ By the end of this module, you'll be able to:
 - Deploy a model to an endpoint and test it in the playground
 - Evaluate model performance using manual and automated approaches
 - Understand different evaluation metrics and when to use them
+
+::: zone-end
+
+> [!NOTE]
+> We recognize that different people like to learn in different ways. You can choose to complete this module in video-based format or you can read the content as text and images. The text contains greater detail than the videos, so in some cases you might want to refer to it as supplemental material to the video presentation.

learn-pr/wwl-data-ai/model-catalog-evaluate/includes/2-explore-model-catalog.md

@@ -1,3 +1,14 @@
+::: zone pivot="video"
+
+>[!VIDEO https://learn-video.azurefd.net/vod/player?id=b7249b09-6632-48fe-bbb4-850fd843b716]
+
+> [!TIP]
+> See the **Text and images** tab for more details!
+
+::: zone-end
+
+::: zone pivot="text"
+
 The Foundry Models catalog serves as your central hub for discovering and comparing AI models. With over 1,900 models available from various providers, you need effective ways to filter and find models that match your specific requirements.
 
 The model catalog includes two broad categories of model:
@@ -57,3 +68,5 @@ The catalog also includes task-specific models:
 ### Regional and domain-specific models
 
 Some models are optimized for specific languages, regions, or industries. When you need specialized performance in a particular domain or language, these models often outperform general-purpose alternatives. Examples include models trained on medical literature, legal documents, or specific language corpora.
+
+::: zone-end

learn-pr/wwl-data-ai/model-catalog-evaluate/includes/3-select-models-benchmarks.md

@@ -1,3 +1,13 @@
+::: zone pivot="video"
+
+>[!VIDEO https://learn-video.azurefd.net/vod/player?id=8ce11522-7c96-423a-96e8-690c57ec232d]
+
+> [!TIP]
+> See the **Text and images** tab for more details!
+
+::: zone-end
+
+::: zone pivot="text"
 Before deploying a model, you want to understand how it performs across different dimensions. Model benchmarks provide objective, measurable data to help you compare models and make informed selection decisions. The Microsoft Foundry portal offers comprehensive benchmarking tools organized into quality, safety, cost, and performance metrics.
 
 ## Access model benchmarks
@@ -95,3 +105,5 @@ The model leaderboard lets you view top models for specific metrics. You can sor
 - Feature support (function calling, structured output, vision)
 
 Select models by checking boxes next to their names, then choose **Compare** to open the detailed comparison view.
+
+::: zone-end

learn-pr/wwl-data-ai/model-catalog-evaluate/includes/4-deploy-models.md

@@ -1,3 +1,14 @@
+::: zone pivot="video"
+
+>[!VIDEO https://learn-video.azurefd.net/vod/player?id=1fc5b011-6d21-45f2-bf26-42d86185fadb]
+
+> [!TIP]
+> See the **Text and images** tab for more details!
+
+::: zone-end
+
+::: zone pivot="text"
+
 After selecting a model from the catalog, you deploy it to make it accessible through endpoints that your applications can use. The Microsoft Foundry portal guides you through the deployment process and provides tools to test your deployed model immediately.
 
 :::image type="content" source="../media/deploy-model.png" alt-text="Screenshot of the Deploy model interface in Foundry portal.":::
@@ -93,3 +104,5 @@ When you're ready to integrate the model into your application, you need three k
 Your application uses these details to construct API requests. The Microsoft Foundry portal provides SDKs and REST API documentation for various programming languages, along with code samples showing request formatting, authentication, and response handling.
 
 With your model deployed and tested, you're ready to integrate it into applications or proceed to more comprehensive evaluation using automated metrics and test datasets.
+
+::: zone-end